模型介紹為中英雙語,中文使用者可以關閉翻譯。
Trubo:
Pornmaster Z Image Turbo Workflow
Pornmaster Z Image Turbo Controlnet Workflow
PornMaster Z-image-turbo Controlnet: Cosplay - Anime to Realistic Style
PornMaster Z-image Increase realism & detail & sharpness
Pornmaster Z-Image Turbo i2i Workflow
PornMaster Simple 4X Magnification Workflow
Pornmaster Z-Image Turbo T2I Workflow-Double checkpoints & realism enhancer
--
Base:
Pornmaster Z Image Base t2i Workflow
--
Stable Diffusion WebUI Forge - Neo
--
如果使用nsfw的lora時,lora權重從0.1開始,然後逐漸增加調整權重。
(可以使用"Z-Image base"的lora,但是需要較高的權重。)
提高照片的解析度可以增加生成良好陰莖和陰部的成功率。
注意:有些人訓練的角色lora可以使用,有些人訓練的則無法使用,我並不知道原因。
如果對生成的性器官不滿意請使用PornMaster SDXL 或PornMaster flux2 klein 9b base 的Inpainting 檢查站來修復性器官。
--
When using nsfw's LoRa, start the LoRa weights from 0.1 and gradually increase them.
(You can use LoRa with a "Z-Image base", but it requires higher weights.)
Increasing the image resolution increases the success rate of generating good-looking penises and genitals.
Note: Some people's character lora training works, while others' does not; I don't know why.
If you are not satisfied with the generated sex organs, please use the Inpainting checkpoint of PornMaster SDXL or PornMaster flux2 klein 9b base to repair the sex organs.
--
Clip: qwen_3_4b.safetensors
Vae: ae.safetensors
--
我已將模型上傳至runninghub。
I have uploaded the model to runninghub.
PornMaster z-image Turbo V0.1_fp8:
https://www.runninghub.ai/model/public/2012876652145020930/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.1_bf16:
https://www.runninghub.ai/model/public/2012891520348725249/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.2_fp8:
https://www.runninghub.ai/model/public/2012870272323424257/?inviteCode=rh-v1304
PornMaster z-image Turbo V0.2_bf16:
https://www.runninghub.ai/model/public/2012858316384374786/?inviteCode=rh-v1304
PornMaster z-image Turbo V1_fp8:
https://www.runninghub.ai/model/public/2015385918403780610/?inviteCode=rh-v1304
PornMaster z-image Turbo V1_bf16:
https://www.runninghub.ai/model/public/2015380234719207425/?inviteCode=rh-v1304
PornMaster z-image Turbo V2_fp8:
https://www.runninghub.ai/model/public/2023636060722434049/?inviteCode=rh-v1304
PornMaster z-image Turbo V2_bf16
https://www.runninghub.ai/model/public/2023630811089604610/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_fp8:
https://www.runninghub.ai/model/public/2024107278651105282/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_bf16:
https://www.runninghub.ai/model/public/2024107273051709442/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_distilled_fp8
https://www.runninghub.ai/model/public/2025833520878325762/?inviteCode=rh-v1304
PornMaster_z-image_base_V0.1_distilled_bf16
https://www.runninghub.ai/model/public/2025836003751108609/?inviteCode=rh-v1304
PornMaster z-image Turbo_5steps_V1_fp8
https://www.runninghub.ai/model/public/2026332244041801729/?inviteCode=rh-v1304
PornMaster z-image Turbo_5steps_V1_bf16
https://www.runninghub.ai/model/public/2026340550038786050/?inviteCode=rh-v1304
PornMaster z-image Turbo V3_fp8
https://www.runninghub.ai/model/public/2040397408881876993/?inviteCode=rh-v1304
PornMaster z-image Turbo V3.5_fp8
https://www.runninghub.ai/model/public/2041355991928807426/?inviteCode=rh-v1304
PornMaster z-image Turbo V3.5_fp16
https://www.runninghub.ai/model/public/2049373402028318721/?inviteCode=rh-v1304
--
不要問我如何安裝的問題與comfyui如何使用。
客製化lora:我的Telegram ID:@iamddtla0620
我的微信ID:iamddtla
我的line ID:iamddtla
時間寶貴,請直接說明來意,例如:訂製lora.
Do not ask me questions about how to install it or how to use ComfyUI.
Customized lora: My Telegram ID: @iamddtla0620
My WeChat ID: iamddtla
My Line ID: iamddtla
Time is precious, please state your intention directly, for example: customized LORA.
Description
時間就是金錢,只需要5步驟就能生成圖片。
依然能夠良好的還原檢查站原本內建的人物。
可以使用Z-Image Turbo和Z-Image Base的lora。
當使用Z-Image Turbo的nsfw lora時,lora權重從0.1開始,然後逐漸增加調整權重。
當使用Z-Image Base的lora時,需要較高的lora權重,權重範圍1~2.5。
--
Time is money. You only need 5 steps to generate images.
It can still accurately reproduce the original built-in checkpoint characters.
Note: Some people's character lora training works, while others' does not; I don't know why.
You can use LoRAs for both Z-Image Turbo and Z-Image Base.
When using the Z-Image Turbo NSFW LoRA, start with a LoRA weight of 0.1 and gradually increase it as needed.
When using the Z-Image Base LoRA, a higher LoRA weight is required, typically in the range of 1 to 2.5.
FAQ
Comments (36)
Turbo_v0.2 bf16版本在用rgthree lora 加载器的时候可以兼容人物lora,效果比较好。
turbo_v1 人物lora用同样的加载器的情况下,也能生成质量尚可的图片,前提是人物lora的权重低一点不要超过0.7
@Bachlee 用lora管理器不行嗎? 是這個嗎? Power Lora Loader (rgthree)?
@iamddtla 是的,我感觉用rgthree的效果要比其他的lora加载器好不少
@Bachlee 謝謝你的回答.
@Bachlee 你有實驗我最新的5步驟版本嗎?
@iamddtla 还没有,我来试试
@iamddtla 我使用了下,你的5步版本真的挺好,皮肤细节完美,阴部形状也正常,就是男性手指偶尔会变成阴茎,人物Lora rgthree在0.6左右权重可以完美使用。
@Bachlee 感謝你的測試.
im looking for something to make proper pussy what do suggest guys?
This is the only lora I have seen for Zit that fixes the missing ass hole issue well: https://civitai.com/models/2406326/simple-rearend-view-female
also does good pussy.
@J1B thanks buddy ill try
At my use, "UniPC-SGM Uniform" combination is best.
比起其他高分模型,大佬您的模型脸部的多样性最好!感谢!
Great work. Base_V0.1 works really well with character LoRas! Im using the distilled 4-step LoRa with this model and a character LoRa.
turbov2 能生成完好的男性和女性阴部,和生成正确的性行为图像,但是使用角色lora后画质有些许劣化,5steps 速度最快,和角色lora兼容也较好,生成的皮肤质感最好,但是在双人交互情况下的容易产生异常。
希望5steps能出个v2,能达到turbov2的多人交互质量,那就完美了。
感谢作者。
training a lora on the distilled 11GB new pornmaster model works pretty good on Ai-Toolkit
anime works flawlessly on it
I am curious though, how do you load the checkpoint? Ai-toolkit only seems to connect and download its models directly from HF in diffuser format, so I have no clue how to use a custom checkpoint like this one to train a lora specifically for it...
@SirColin
go to one of your jobs in this folder
ai-toolkit/ui/src/app/jobs/new/options.ts
change
'config.process[0].model.name_or_path': ['Tongyi-MAI/Z-Image', defaultNameOrPath],
to
'config.process[0].model.name_or_path': ['Tongyi-MAI/Z-Image', '/your_path_from_addressbar/pornmasterZImage_distilledV01.safetensors'],
instead of downloading the model which is annoying because alot of people clear cache often, it will redirect to your model you put there allowing you to train ontop of it.
then follow this https://www.youtube.com/watch?v=Kmve1_jiDpQ
to get a good base for configuring it( I just set mines to 3000 steps) and surprisingly turbo configurations work for the distilled zimage model
dm or reply for further help, I have to goon now my people need me.
@Docuei Thank you for your advice, but I have tried with the ai-toolkit that gives me this error message: "We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like B:/AI_Toolkit_SECourses_v11_ - copy/model/pornmasterZImage_distilledV01.safetensors\transformer is not the path to a directory containing a config.json file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'." Grateful to have some more guidelines, thank you!
sorry im new to z image, ive downloaded the gguf but where can i actually use it, ive downloaded your simple workflow and i only see that i can use diffusion models not the pornmaster gguf ive downloaded. ive tried placing the gguf in the diffusion model folder or adding a load checkpoint node but nothing is working
I did not create the gguf file.
put it in the models/unet folder
You need to download the comfyui-GGUF node package and use the GGUF loading node
z image base checkpoint is goat .. powerful ... i can't wait v2 base checkpoint
really liked your other checkpoints for other models, but this one cant even do a simple bj or missionary pose.
Using distilled base and it's pretty good but it does a bad job at genitals. I have model shift at 3, CFG between 1-2, 10-20 steps, and have tried many samplers getting best results with res2.
Hi, anyone knows how to get correct penises? as well as correct penetration?
I'm using the V1 and V2 for Turbo but they come out weird.
Also, should I use something else instead of Turbo if I want to get better results? I am mostly using IMAGE 2 IMAGE for my work.
why most of these checkpoints are overwhelmed with female photos? is it not capable of creating male figures?
Z image is known to struggle with the male anatomy.
Using Turbo_V2, can't even do vaginal penetration. No matter what I prompt, it's always anal.
I use inpaint for the SDXL model in A1111 to refine the image received in ZIT. ZIT is an ideal basis for realism, but it requires further processing.



















